BITE: Skill for Claude Code

.claude/skills/papers-audit-metadata-consistency/SKILL.md

papers-audit-metadata-consistency is a skill for Claude Code from RipeMangoBox/BITE. It costs 60 tokens per session (480 once invoked), scanned A, original, MIT.

A metadata quality check for a research-paper workflow. It compares paper lists, logs, and analysis notes for matching titles, venues, years, links, files, duplicates, and required note structure.

In plain words
What is it for?
It is for auditing an Obsidian-based paper archive and writing a quality report about inconsistent metadata, missing records, duplicates, and malformed analysis notes.
Why use it?
It finds organizational and record-keeping problems that can make a paper collection unreliable, such as missing links, duplicate entries, or notes that do not match the source list.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is RipeMangoBox/BITE's own configuration. It tells Claude Code how to work on BITE itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything BITE configures →

Reuse

Borrowing it

Nothing to install: this file belongs to RipeMangoBox/BITE. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/RipeMangoBox/BITE/main/.claude/skills/papers-audit-metadata-consistency/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/RipeMangoBox/BITE

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for papers-audit-metadata-consistency

README.md
[![agentmods](https://agentmods.dev/badge/skills/ripemangobox/bite/papers-audit-metadata-consistency.svg)](https://agentmods.dev/skills/ripemangobox/bite/papers-audit-metadata-consistency)
Your own site
<a href="https://agentmods.dev/skills/ripemangobox/bite/papers-audit-metadata-consistency"><img src="https://agentmods.dev/badge/skills/ripemangobox/bite/papers-audit-metadata-consistency.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 480 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00060 $0.00480
Opus 5 $0.00030 $0.00240
Sonnet 5 $0.00012 $0.00096
Haiku 4.5 $0.00006 $0.00048

Measured 8d ago against content hash c3a05e027a74, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

papers-audit-metadata-consistency scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 8d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/audit_metadata_consistency.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/papers-audit-metadata-consistency/SKILL.md · 61 lines

What it actually says

Metadata Consistency Audit

What this skill does

Runs one unified audit entry for step5 quality governance:

  • checks obsidian-vault/paper_list.csv and legacy list/log entries when present;
  • checks obsidian-vault/analysis/**/*.md analysis notes;
  • checks cross-layer consistency between log/list and analysis notes;
  • outputs obsidian-vault/batches/reports/quality_report_*.md (optionally .json).

Coverage

This skill covers structural and metadata hygiene only.

  • title / venue / year consistency
  • link completeness (paper_link, project_link/github_link, pdf_ref)
  • duplicate paper detection in txt logs
  • analysis note structure anomalies (missing frontmatter keys, missing semantic analysis sections)
  • unmatched records (only-in-txt, only-in-md)

Current limits

  • does not evaluate whether conclusions are sufficiently supported by evidence
  • does not score citation quality in idea notes or share notes
  • does not audit completeness of comparison tables or downstream summaries
  • does not detect stale analyses that should be refreshed
  • broader semantic-layer governance belongs to a future knowledge-hygiene / evidence-governance extension

Run

From the repository root:

python3 .claude/skills/papers-audit-metadata-consistency/scripts/audit_metadata_consistency.py

Optional JSON output:

python3 .claude/skills/papers-audit-metadata-consistency/scripts/audit_metadata_consistency.py --json

Output

  • obsidian-vault/batches/reports/quality_report_<YYYY-MM-DD_HHMM>.md
  • optional obsidian-vault/batches/reports/quality_report_<YYYY-MM-DD_HHMM>.json

When to use

  • after collect/download/analyze batches
  • before rebuilding indexes
  • periodic KB quality checks for open-source readiness
Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 8d ago First seen · 61 lines · 60 tokens per session scan A c3a05e027a74

Subscribe to this mod's changes

papers-audit-metadata-consistency is a skill published in the GitHub repository RipeMangoBox/BITE (61 stars, last pushed 25d ago), licensed MIT. It adds 60 tokens to every session and 480 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

results-report

A workflow for turning completed experiment analyses into a structured research report with findings, limitations, failures, and next steps.

Galaxy-Dawn/claude-scholar · 78 tokens

results-analysis

This skill should be used when the user asks to "analyze experimental results", "run strict statistical analysis", "compare model performance", "generate scientific figures", "check significance", "do ablation analysis", or mentions interpreting experiment data with rigorous statistics and visualization. It focuses on…

Galaxy-Dawn/claude-scholar · 68 tokens

nature-data

Prepare, audit, or revise Nature-ready Data Availability statements, data repository plans, dataset citations, and FAIR metadata checklists for manuscripts. Use when the user asks about Nature data availability, research data sharing, repository selection, accession numbers, restricted or sensitive data, source data…

Galaxy-Dawn/claude-scholar · 90 tokens

nature-response

Draft, audit, or revise point-by-point reviewer response letters for Nature-family manuscript revisions. Use when the user provides reviewer comments, editor decision letters, revision notes, response drafts, or asks how to respond to major/minor revision requests, rebuttal letters, response to reviewers, peer-review…

Galaxy-Dawn/claude-scholar · 91 tokens

paper-self-review

This skill should be used when the user asks to "review paper quality", "check paper completeness", "validate paper structure", "self-review before submission", "audit claims", "check overclaiming", "verify whether results support claims", or mentions systematic paper quality checking. Provides comprehensive quality…

Galaxy-Dawn/claude-scholar · 68 tokens

post-acceptance

This skill should be used when the user asks to "prepare conference presentation", "create presentation slides", "design poster", "make academic poster", "write promotion content", "create Twitter thread", or mentions post-acceptance conference preparation. Provides comprehensive workflow for presentation, poster, and…

Galaxy-Dawn/claude-scholar · 66 tokens